One of the most challenging issues in the analysis of large collections of historical manuscripts or handwritten fragments is the "joining" of fragments, either piecing together torn parts of a mutilated folio – which may have disintegrated because of wear and tear over the ages – or reconnecting two or more folios originating from the same original manuscript, but which have since been separated and dispersed to diverse locations – perhaps on account of trading activities between institutions. A striking case in point is the Cairo Genizah, discovered towards the end of the nineteenth century in the attic of an old synagogue in Cairo, which contains more than 320,000 fragments (deriving from tens of thousands of individual documents, almost all in Hebrew characters – though not necessarily in the Hebrew language) spanning a thousand years of writing and copying. Various parts of the Genizah finds are currently located in more than sixty university collections and public libraries spread out on different continents all over the world. Until just recently, a Genizah researcher holding half a page in hand and seeking its other half, did not have any resources with which to achieve that goal beyond erudition, a few catalogs, a gifted memory, and a fair measure of luck.
[1]
Gregory Bearman.
Imaging the Dead Sea Scrolls for conservation purposes
,
2008
.
[2]
Jieh Hsiang,et al.
On Building a Full-Text Digital Library of Land Deeds of Taiwan
,
2009
.
[3]
Lior Wolf,et al.
Identifying Join Candidates in the Cairo Genizah
,
2011,
International Journal of Computer Vision.
[4]
Tim Weyrich,et al.
A system for high-volume acquisition and matching of fresco fragments: reassembling Theran wall paintings
,
2008,
ACM Trans. Graph..
[5]
Tal Hassner,et al.
The One-Shot similarity kernel
,
2009,
2009 IEEE 12th International Conference on Computer Vision.
[6]
Tim Weyrich,et al.
A system for high-volume acquisition and matching of fresco fragments: reassembling Theran wall paintings
,
2008,
SIGGRAPH 2008.